import pandas as pd 
import numpy as np 
import matplotlib
from pandas_profiling import ProfileReport
import matplotlib.pyplot as plt
import seaborn as sns
from warnings import filterwarnings
%matplotlib inline
from mpl_toolkits.mplot3d import Axes3D

df = pd.read_csv(("cancer_data.csv"))
df

	Gender	Symptoms	Alcohol	Hepatitis B Surface Antigen	Hepatitis B e Antigen	Hepatitis B Core Antibody	Hepatitis C Virus Antibody	Cirrhosis	Endemic Countries	Smoking	...	Alkaline phosphatase (U/L)	Total Proteins (g/dL)	Creatinine (mg/dL)	Number of Nodules	Major dimension of nodule (cm)	Direct Bilirubin (mg/dL)	Iron (mcg/dL)	Oxygen Saturation (%)	Ferritin	Class
0	1	0	1	0	0	0	0	1	0	1	...	150.0	7.1	0.70	1	3.5	0.50	86.0	37.0	435.0	1
1	0	1	0	0	0	0	1	1	0	1	...	215.0	8.7	2.95	1	1.8	1.96	86.0	37.0	435.0	1
2	1	0	1	1	0	1	0	1	0	1	...	109.0	7.0	2.10	5	13.0	0.10	28.0	6.0	16.0	1
3	1	1	1	0	0	0	0	1	0	1	...	174.0	8.1	1.11	2	15.7	0.20	86.0	37.0	435.0	0
4	1	1	1	1	0	1	0	1	0	1	...	109.0	6.9	1.80	1	9.0	1.96	59.0	15.0	22.0	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
126	1	0	0	0	0	0	1	1	0	1	...	117.0	7.2	0.69	1	13.0	0.70	86.0	37.0	435.0	1
127	1	0	1	0	0	0	0	1	0	0	...	182.0	6.2	0.77	2	4.3	1.00	93.0	47.0	307.0	1
128	1	0	0	1	0	0	0	1	0	1	...	127.0	6.9	1.11	2	4.3	1.96	28.0	10.0	308.0	0
129	0	1	1	0	0	0	0	1	0	0	...	171.0	7.1	0.66	2	5.8	1.96	86.0	37.0	435.0	0
130	0	1	0	0	0	0	0	1	0	0	...	150.0	5.4	0.70	5	17.5	0.30	86.0	37.0	435.0	1

131 rows × 50 columns

We can see many of 0 & 1 values in the data set, So, We'll take 0 As Female & 1 as Male

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 131 entries, 0 to 130
Data columns (total 50 columns):
 #   Column                            Non-Null Count  Dtype  
---  ------                            --------------  -----  
 0   Gender                            131 non-null    int64  
 1   Symptoms                          131 non-null    int64  
 2   Alcohol                           131 non-null    int64  
 3   Hepatitis B Surface Antigen       131 non-null    int64  
 4   Hepatitis B e Antigen             131 non-null    int64  
 5   Hepatitis B Core Antibody         131 non-null    int64  
 6   Hepatitis C Virus Antibody        131 non-null    int64  
 7   Cirrhosis                         131 non-null    int64  
 8   Endemic Countries                 131 non-null    int64  
 9   Smoking                           131 non-null    int64  
 10  Diabetes                          131 non-null    int64  
 11  Obesity                           131 non-null    int64  
 12  Hemochromatosis                   131 non-null    int64  
 13  Arterial Hypertension             131 non-null    int64  
 14  Chronic Renal Insufficiency       131 non-null    int64  
 15  Human Immunodeficiency Virus      131 non-null    int64  
 16  Nonalcoholic Steatohepatitis      131 non-null    int64  
 17  Esophageal Varices                131 non-null    int64  
 18  Splenomegaly                      131 non-null    int64  
 19  Portal Hypertension               131 non-null    int64  
 20  Portal Vein Thrombosis            131 non-null    int64  
 21  Liver Metastasis                  131 non-null    int64  
 22  Radiological Hallmark             131 non-null    int64  
 23  Age at diagnosis                  131 non-null    int64  
 24  Grams of Alcohol per day          131 non-null    int64  
 25  Packs of cigarets per year:       131 non-null    float64
 26  Performance Status                131 non-null    int64  
 27  Encefalopathy degree              131 non-null    int64  
 28  Ascites degree                    131 non-null    int64  
 29  International Normalised Ratio:   131 non-null    float64
 30  Alpha-Fetoprotein (ng/mL)         131 non-null    float64
 31  Haemoglobin (g/dL)                131 non-null    float64
 32  Mean Corpuscular Volume (fl)      131 non-null    float64
 33  Leukocytes(G/L)                   131 non-null    float64
 34  Platelets (G/L)                   131 non-null    float64
 35  Albumin (mg/dL)                   131 non-null    float64
 36  Total Bilirubin(mg/dL)            131 non-null    float64
 37  Alanine transaminase (U/L)        131 non-null    float64
 38  Aspartate transaminase (U/L)      131 non-null    int64  
 39  Gamma glutamyl transferase (U/L)  131 non-null    float64
 40  Alkaline phosphatase (U/L)        131 non-null    float64
 41  Total Proteins (g/dL)             131 non-null    float64
 42  Creatinine (mg/dL)                131 non-null    float64
 43  Number of Nodules                 131 non-null    int64  
 44  Major dimension of nodule (cm)    131 non-null    float64
 45  Direct Bilirubin (mg/dL)          131 non-null    float64
 46  Iron (mcg/dL)                     131 non-null    float64
 47  Oxygen Saturation (%)             131 non-null    float64
 48  Ferritin                          131 non-null    float64
 49  Class                             131 non-null    int64  
dtypes: float64(19), int64(31)
memory usage: 51.3 KB

count_gender = df.loc[df.Gender].count()[0]
count_gender # count of gender data 

131

#converting all columns containing 0 & 1 numnbers denoting male and female values

list = [df.columns[0:23]]

for i in list:
    df[i] = df[i].replace([1], "male")
    df[i] = df[i].replace([0], "female")

df.head() #values are changed

	Gender	Symptoms	Alcohol	Hepatitis B Surface Antigen	Hepatitis B e Antigen	Hepatitis B Core Antibody	Hepatitis C Virus Antibody	Cirrhosis	Endemic Countries	Smoking	...	Alkaline phosphatase (U/L)	Total Proteins (g/dL)	Creatinine (mg/dL)	Number of Nodules	Major dimension of nodule (cm)	Direct Bilirubin (mg/dL)	Iron (mcg/dL)	Oxygen Saturation (%)	Ferritin	Class
0	male	female	male	female	female	female	female	male	female	male	...	150.0	7.1	0.70	1	3.5	0.50	86.0	37.0	435.0	1
1	female	male	female	female	female	female	male	male	female	male	...	215.0	8.7	2.95	1	1.8	1.96	86.0	37.0	435.0	1
2	male	female	male	male	female	male	female	male	female	male	...	109.0	7.0	2.10	5	13.0	0.10	28.0	6.0	16.0	1
3	male	male	male	female	female	female	female	male	female	male	...	174.0	8.1	1.11	2	15.7	0.20	86.0	37.0	435.0	0
4	male	male	male	male	female	male	female	male	female	male	...	109.0	6.9	1.80	1	9.0	1.96	59.0	15.0	22.0	1

5 rows × 50 columns

Pandas Profiling Report

# from pandas_profiling import ProfileReport

# profile = ProfileReport(df)
# profile.to_file(output_file = "cancer_data.html" ) # creation of pandas profile report for easy understanding of the data

df.shape # there are 40260 rows and 7 columns of data

(131, 50)

In Data Analysis We will Analyze To Find out the below stuff

1. Missing Values

2. All The Numerical Variables

3. Distribution of the Numerical Variables

4. Categorical Variables

5. Outliers

6. Relationship between independent and dependent feature(SalePrice)

1. Missing Values

## Here we will check the percentage of nan values present in each feature

## 1 -step make the list of features which has missing values

features_with_na=[features for features in df.columns if df[features].isnull().sum()>1] #list comprehension use

## 2- step print the feature name and the percentage of missing values

for feature in features_with_na:
    print(feature, np.round(df[feature].isnull().mean(), 4),  ' % missing values')

There are no missing values in the data set

2. All The Numerical Variables

numerical_features = [feature for feature in df.columns if df[feature].dtypes != 'O'] # list comprehension feature that are not equal to object type

print('Number of numerical variables: ', len(numerical_features))

# visualise the numerical variables
df[numerical_features].head()

Number of numerical variables:  27

	Age at diagnosis	Grams of Alcohol per day	Packs of cigarets per year:	Performance Status	Encefalopathy degree	Ascites degree	International Normalised Ratio:	Alpha-Fetoprotein (ng/mL)	Haemoglobin (g/dL)	Mean Corpuscular Volume (fl)	...	Alkaline phosphatase (U/L)	Total Proteins (g/dL)	Creatinine (mg/dL)	Number of Nodules	Major dimension of nodule (cm)	Direct Bilirubin (mg/dL)	Iron (mcg/dL)	Oxygen Saturation (%)	Ferritin	Class
0	67	137	15.0	0	1	1	1.53	95.0	13.70	106.6	...	150.0	7.1	0.70	1	3.5	0.50	86.0	37.0	435.0	1
1	62	0	23.0	0	1	1	1.39	22427.0	12.79	94.5	...	215.0	8.7	2.95	1	1.8	1.96	86.0	37.0	435.0	1
2	78	50	50.0	2	1	2	0.96	5.8	8.90	79.8	...	109.0	7.0	2.10	5	13.0	0.10	28.0	6.0	16.0	1
3	77	40	30.0	0	1	1	0.95	2440.0	13.40	97.1	...	174.0	8.1	1.11	2	15.7	0.20	86.0	37.0	435.0	0
4	76	100	30.0	0	1	1	0.94	49.0	14.30	95.1	...	109.0	6.9	1.80	1	9.0	1.96	59.0	15.0	22.0	1

5 rows × 27 columns

numerical_features

['Age at diagnosis',
 'Grams of Alcohol per day',
 'Packs of cigarets per year:',
 'Performance Status',
 'Encefalopathy degree',
 'Ascites degree',
 'International Normalised Ratio:',
 'Alpha-Fetoprotein (ng/mL)',
 'Haemoglobin (g/dL)',
 'Mean Corpuscular Volume (fl)',
 'Leukocytes(G/L)',
 'Platelets (G/L)',
 'Albumin (mg/dL)',
 'Total Bilirubin(mg/dL)',
 'Alanine transaminase (U/L)',
 'Aspartate transaminase (U/L)',
 'Gamma glutamyl transferase (U/L)',
 'Alkaline phosphatase (U/L)',
 'Total Proteins (g/dL)',
 'Creatinine (mg/dL)',
 'Number of Nodules',
 'Major dimension of nodule (cm)',
 'Direct Bilirubin (mg/dL)',
 'Iron (mcg/dL)',
 'Oxygen Saturation (%)',
 'Ferritin',
 'Class']

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 131 entries, 0 to 130
Data columns (total 50 columns):
 #   Column                            Non-Null Count  Dtype  
---  ------                            --------------  -----  
 0   Gender                            131 non-null    object 
 1   Symptoms                          131 non-null    object 
 2   Alcohol                           131 non-null    object 
 3   Hepatitis B Surface Antigen       131 non-null    object 
 4   Hepatitis B e Antigen             131 non-null    object 
 5   Hepatitis B Core Antibody         131 non-null    object 
 6   Hepatitis C Virus Antibody        131 non-null    object 
 7   Cirrhosis                         131 non-null    object 
 8   Endemic Countries                 131 non-null    object 
 9   Smoking                           131 non-null    object 
 10  Diabetes                          131 non-null    object 
 11  Obesity                           131 non-null    object 
 12  Hemochromatosis                   131 non-null    object 
 13  Arterial Hypertension             131 non-null    object 
 14  Chronic Renal Insufficiency       131 non-null    object 
 15  Human Immunodeficiency Virus      131 non-null    object 
 16  Nonalcoholic Steatohepatitis      131 non-null    object 
 17  Esophageal Varices                131 non-null    object 
 18  Splenomegaly                      131 non-null    object 
 19  Portal Hypertension               131 non-null    object 
 20  Portal Vein Thrombosis            131 non-null    object 
 21  Liver Metastasis                  131 non-null    object 
 22  Radiological Hallmark             131 non-null    object 
 23  Age at diagnosis                  131 non-null    int64  
 24  Grams of Alcohol per day          131 non-null    int64  
 25  Packs of cigarets per year:       131 non-null    float64
 26  Performance Status                131 non-null    int64  
 27  Encefalopathy degree              131 non-null    int64  
 28  Ascites degree                    131 non-null    int64  
 29  International Normalised Ratio:   131 non-null    float64
 30  Alpha-Fetoprotein (ng/mL)         131 non-null    float64
 31  Haemoglobin (g/dL)                131 non-null    float64
 32  Mean Corpuscular Volume (fl)      131 non-null    float64
 33  Leukocytes(G/L)                   131 non-null    float64
 34  Platelets (G/L)                   131 non-null    float64
 35  Albumin (mg/dL)                   131 non-null    float64
 36  Total Bilirubin(mg/dL)            131 non-null    float64
 37  Alanine transaminase (U/L)        131 non-null    float64
 38  Aspartate transaminase (U/L)      131 non-null    int64  
 39  Gamma glutamyl transferase (U/L)  131 non-null    float64
 40  Alkaline phosphatase (U/L)        131 non-null    float64
 41  Total Proteins (g/dL)             131 non-null    float64
 42  Creatinine (mg/dL)                131 non-null    float64
 43  Number of Nodules                 131 non-null    int64  
 44  Major dimension of nodule (cm)    131 non-null    float64
 45  Direct Bilirubin (mg/dL)          131 non-null    float64
 46  Iron (mcg/dL)                     131 non-null    float64
 47  Oxygen Saturation (%)             131 non-null    float64
 48  Ferritin                          131 non-null    float64
 49  Class                             131 non-null    int64  
dtypes: float64(19), int64(8), object(23)
memory usage: 51.3+ KB

a = 9  # number of rows
b = 3  # number of columns
c = 1  # initialize plot counter

fig = plt.figure(figsize=(20,55))

for i in numerical_features[0:26]:
    plt.subplot(a, b, c)
    plt.title('{}, subplot: {}{}{}'.format(i, a, b, c))

    sns.histplot(data= df, x= i, hue="Gender")
    # plt.title(f" Gender vs {i}")

    c = c + 1

plt.show()

let us check for decreate values

## Numerical variables are usually of 2 type
## 1. Continous variable and Discrete Variables

discrete_feature=[feature for feature in numerical_features if len(df[feature].unique())<25]
print("Discrete Variables Count: {}".format(len(discrete_feature)))

Discrete Variables Count: 6

df[discrete_feature].head()

	Grams of Alcohol per day	Performance Status	Encefalopathy degree	Ascites degree	Number of Nodules	Class
0	137	0	1	1	1	1
1	0	0	1	1	1	1
2	50	2	1	2	5	1
3	40	0	1	1	2	0
4	100	0	1	1	1	1

discrete_feature

['Grams of Alcohol per day',
 'Performance Status',
 'Encefalopathy degree',
 'Ascites degree',
 'Number of Nodules',
 'Class']

a = 2  # number of rows
b = 3  # number of columns
c = 1  # initialize plot counter

fig = plt.figure(figsize=(20,15))

for i in discrete_feature:
    plt.subplot(a, b, c)
    plt.title('{}, subplot: {}{}{}'.format(i, a, b, c))

    sns.boxplot(x="Gender", y = i ,data=df)
      
    # plt.title(f" Gender vs {i}")

    c = c + 1

plt.show()

Continous Features

continuous_feature=[feature for feature in numerical_features if feature not in discrete_feature ]
print("Continuous feature Count {}".format(len(continuous_feature)))

Continuous feature Count 21

continuous_feature
len(continuous_feature)

21

a = 7  # number of rows
b = 3  # number of columns
c = 1  # initialize plot counter

fig = plt.figure(figsize=(20,55))

for i in continuous_feature:
    plt.subplot(a, b, c)
    plt.title('{}  , subplot: {}{}{}'.format(i, a, b, c))

    sns.histplot(data= df, x= i, hue="Gender", element="poly")

    c = c + 1

plt.show()

OUTLIERS

a = 7  # number of rows
b = 3  # number of columns
c = 1  # initialize plot counter

fig = plt.figure(figsize=(20,55))

plt.style.use("ggplot")

for i in continuous_feature:
    data=df.copy()

    if 0 in data[i].unique():
        pass
    else:
        plt.subplot(a, b, c)
        plt.title('{}, subplot: {}{}{}'.format(i, a, b, c))

        sns.boxplot(x="Gender", y = i ,data=df)

        c = c + 1

plt.show()

categorical vairables

categorical_features=[feature for feature in df.columns if df[feature].dtypes=='O']
categorical_features

['Gender',
 'Symptoms',
 'Alcohol',
 'Hepatitis B Surface Antigen',
 'Hepatitis B e Antigen',
 'Hepatitis B Core Antibody',
 'Hepatitis C Virus Antibody',
 'Cirrhosis',
 'Endemic Countries',
 'Smoking',
 'Diabetes',
 'Obesity',
 'Hemochromatosis',
 'Arterial Hypertension',
 'Chronic Renal Insufficiency',
 'Human Immunodeficiency Virus',
 'Nonalcoholic Steatohepatitis',
 'Esophageal Varices',
 'Splenomegaly',
 'Portal Hypertension',
 'Portal Vein Thrombosis',
 'Liver Metastasis',
 'Radiological Hallmark']

df[categorical_features].head()

	Gender	Symptoms	Alcohol	Hepatitis B Surface Antigen	Hepatitis B e Antigen	Hepatitis B Core Antibody	Hepatitis C Virus Antibody	Cirrhosis	Endemic Countries	Smoking	...	Arterial Hypertension	Chronic Renal Insufficiency	Human Immunodeficiency Virus	Nonalcoholic Steatohepatitis	Esophageal Varices	Splenomegaly	Portal Hypertension	Portal Vein Thrombosis	Liver Metastasis	Radiological Hallmark
0	male	female	male	female	female	female	female	male	female	male	...	female	female	female	female	male	female	female	female	female	male
1	female	male	female	female	female	female	male	male	female	male	...	male	female	female	female	male	female	female	female	female	male
2	male	female	male	male	female	male	female	male	female	male	...	male	male	female	female	female	female	male	female	male	male
3	male	male	male	female	female	female	female	male	female	male	...	male	female	female	female	female	female	female	female	male	male
4	male	male	male	male	female	male	female	male	female	male	...	male	male	female	female	female	female	female	female	female	male

5 rows × 23 columns

for feature in categorical_features:
    print('The feature is {} and number of categories are {}'.format(feature,len(df[feature].unique())))

The feature is Gender and number of categories are 2
The feature is Symptoms and number of categories are 2
The feature is Alcohol and number of categories are 2
The feature is Hepatitis B Surface Antigen and number of categories are 2
The feature is Hepatitis B e Antigen and number of categories are 2
The feature is Hepatitis B Core Antibody and number of categories are 2
The feature is Hepatitis C Virus Antibody and number of categories are 2
The feature is Cirrhosis and number of categories are 2
The feature is Endemic Countries and number of categories are 2
The feature is Smoking and number of categories are 2
The feature is Diabetes and number of categories are 2
The feature is Obesity and number of categories are 2
The feature is Hemochromatosis and number of categories are 2
The feature is Arterial Hypertension and number of categories are 2
The feature is Chronic Renal Insufficiency and number of categories are 2
The feature is Human Immunodeficiency Virus and number of categories are 2
The feature is Nonalcoholic Steatohepatitis and number of categories are 2
The feature is Esophageal Varices and number of categories are 2
The feature is Splenomegaly and number of categories are 2
The feature is Portal Hypertension and number of categories are 2
The feature is Portal Vein Thrombosis and number of categories are 2
The feature is Liver Metastasis and number of categories are 2
The feature is Radiological Hallmark and number of categories are 2

len(categorical_features)

23

a = 8  # number of rows
b = 3  # number of columns
c = 1  # initialize plot counter

fig = plt.figure(figsize=(20,55))
plt.style.use("ggplot")

for i in categorical_features:
    plt.subplot(a, b, c)
    plt.title('{} vs Cancer'.format(i))
    df[i].value_counts().plot(kind='pie', autopct='%.4f')
    plt.legend(loc = "best")
    

    c = c + 1

plt.show()